This script is used for modeling pH of the particluar geochemical system

import pickle
import numpy as np
import pandas as pd
import os
import seaborn as sns
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, mean_absolute_error,mean_squared_error,r2_score

## The following are the ML models which can be used for trasinning
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import Matern
from sklearn.linear_model import LinearRegression

from sklearn.preprocessing import MinMaxScaler,StandardScaler

import timeit
import warnings
warnings.filterwarnings("ignore")

import matplotlib.pyplot as plt
import matplotlib as mpl

import numpy as np
%matplotlib inline
import pandas as pd

import plotly.express as px

import seaborn as sns
sns.set(style="darkgrid")

sns.set_context('talk')

data_dir =r'E:\projects\MLChemicalR\uranium\20_training_sets\30_phreeqc'
datafiles = os.listdir(data_dir)
datafiles =[fl for fl in datafiles if 'dat' in fl]

out_dir = os.path.join(data_dir,'output')
if not os.path.exists(out_dir):
    os.mkdir(out_dir)

datafiles

['10_PMU_02_LHS_500000_54854_02_t_P.dat',
 '10_PMU_02_LHS_50000_54854_02_t_P.dat',
 '10_PMU_02_LHS_5000_54854_02_t_P.dat',
 '10_PMU_02_LHS_500_54854_02_t_P.dat']

dataset_all={}
for file in datafiles:
    InsFile = os.path.join(data_dir, file)
    data = pd.read_csv(InsFile,sep ='\t')
    data.columns =[col.strip() for col in data.columns]
    data =data.iloc[:-1,:-1]
    dataset_all[file[:-4]] = data

data50K =dataset_all['10_PMU_02_LHS_50000_54854_02_t_P']

data50K['diff'] = data50K['totBase']-data50K['totAcid']

conditions = [
    (data50K['pH'] < 7),
    (data50K['pH'] ==7),
    (data50K['pH'] > 7),
    ]
# create a list of the values we want to assign for each condition
values = [1, 2, 3]
data50K['GrouppH'] = np.select(conditions, values)

conditions = [
    (data50K['metaschoepite'] ==0),
    (data50K['metaschoepite'] >0),
    ]
# create a list of the values we want to assign for each condition
values = [1, 2]
data50K['GroupMeta'] = np.select(conditions, values)

data50K.tail()

	mass_H2O	totU	totAcid	totBase	pH	U_aq	U_s	U_sc	U_ex	Kd_s	Kd_sc	Kd_ex	metaschoepite	diff	GrouppH	GroupMeta
49994	0.999894	9.095900e-05	1.000000e-09	1.871300e-02	12.1360	8.897400e-05	1.995000e-06	1.995000e-06	2.309200e-22	22.422	22.42200	2.595400e-15	0.0	0.018713	3	1
49995	1.000060	2.817900e-07	1.000000e-09	8.701300e-04	10.7810	1.221800e-08	2.695800e-07	2.695800e-07	1.414000e-21	22064.000	22064.00000	1.157400e-10	0.0	0.000870	3	1
49996	1.000020	4.389100e-05	1.000000e-09	5.106400e-03	11.5710	4.189600e-05	1.994800e-06	1.994800e-06	1.342100e-20	47.614	47.61400	3.203500e-13	0.0	0.005106	3	1
49997	0.999935	1.016900e-05	1.422900e-02	1.000000e-09	1.9613	9.511300e-06	6.582500e-07	2.240300e-09	6.560100e-07	69.208	0.23555	6.897200e+01	0.0	-0.014229	1	1
49998	0.999928	5.609300e-09	1.493300e-02	1.000000e-09	1.9398	5.246100e-09	3.636500e-10	1.118100e-12	3.625300e-10	69.319	0.21313	6.910500e+01	0.0	-0.014933	1	1

fig = px.scatter_3d(data50K, x='diff', y='totU', z='pH',color='pH',symbol ='GroupMeta')
fig.show()

fig = px.scatter_3d(data50K, x='diff', y='totU', z='U_s',color='pH',symbol ='GroupMeta')
fig.show()

fig = px.scatter_3d(data50K, x='diff', y='totU', z='U_aq',color='pH',symbol ='GroupMeta')
fig.show()

fig = px.scatter_3d(data50K, x='diff', y='totU', z='U_sc',color='pH',symbol ='GroupMeta')
fig.show()

fig = px.scatter_3d(data50K, x='diff', y='totU', z='U_ex',color='pH',symbol ='GroupMeta')
fig.show()

fig = px.scatter_3d(data50K, x='diff', y='totU', z='metaschoepite',color='pH',symbol ='GroupMeta')
fig.show()

data50K.columns

Index(['mass_H2O', 'totU', 'totAcid', 'totBase', 'pH', 'U_aq', 'U_s', 'U_sc',
       'U_ex', 'Kd_s', 'Kd_sc', 'Kd_ex', 'metaschoepite', 'diff', 'GrouppH',
       'GroupMeta'],
      dtype='object')